4 papers · 1 filter
PragAlign: Feedback-Guided Pragmatic Alignment for Controlled Synthetic Dialogue Generation
Smitha Muthya Sudheendra, Jaideep Srivastava
Synthetic dialogue generation can support research in privacy-restricted service settings, but generated conversations must preserve communicative intent, affective meaning, and na…
When Decodability Is Not Enough: Logical Validity Representations, Behavioral Dissociation, and Causal Tests in Language Models
Smitha Muthya Sudheendra, Jaideep Srivastava
Large language models can look capable of logical reasoning, but correct or incorrect answers alone tell us little about what the model represents internally. We study logical veri…
BiMind: A Dual-Head Reasoning Model with Attention-Geometry Adapter for Incorrect Information Detection
Zhongxing Zhang, Emily K. Vraga, Jisu Huh +1
Incorrect information poses significant challenges by disrupting content veracity and integrity, yet most detection approaches struggle to jointly balance textual content verificat…
ReasonScaffold: A Scaffolded Reasoning-based Annotation Protocol for Human-AI Co-Annotation
Smitha Muthya Sudheendra, Jaideep Srivastava
Human annotation is central to NLP evaluation, yet subjective tasks often exhibit substantial variability across annotators. While large language models (LLMs) can provide structur…